Search Results for author:
Found 34 papers, 10 papers with code
Cost-Sensitive Learning to Defer to Multiple Experts with Workload Constraints
Learning to defer (L2D) aims to improve human-AI collaboration systems by learning how to defer decisions to humans when they are more likely to be correct than an ML classifier.
DiConStruct: Causal Concept-based Explanations through Black-Box Distillation
Lastly, explanation methods should be efficient and not compromise the performance of the predictive task.
FiFAR: A Fraud Detection Dataset for Learning to Defer
Financial fraud detection is a high-stakes setting where algorithms and human experts often work in tandem; however, there are no publicly available datasets for L2D concerning this important application of human-AI teaming.
Fairness-Aware Data Valuation for Supervised Learning
Data valuation is a ML field that studies the value of training instances towards a given predictive task.
Distinguishing Cause from Effect on Categorical Data: The Uniform Channel Model
We select as the most likely causal direction the one in which the conditional pmf is closer to a uniform channel (UC).
ProBoost: a Boosting Method for Probabilistic Classifiers
ProBoost, a new boosting algorithm for probabilistic classifiers, is proposed in this work.
Understanding Unfairness in Fraud Detection through Model and Data Bias Interactions
The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within.
Human-AI Collaboration in Decision-Making: Beyond Learning to Defer
Human-AI collaboration (HAIC) in decision-making aims to create synergistic teaming between human decision-makers and AI systems.
Prisoners of Their Own Devices: How Models Induce Data Bias in Performative Prediction
The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within.
Differentiable Causal Discovery Under Latent Interventions
Recent work has shown promising results in causal discovery by leveraging interventional data with gradient-based methods, even when the intervened variables are unknown.
Sparse Continuous Distributions and Fenchel-Young Losses
In contrast, for finite domains, recent work on sparse alternatives to softmax (e. g., sparsemax, $\alpha$-entmax, and fusedmax), has led to distributions with varying support.
TimeSHAP: Explaining Recurrent Models through Sequence Perturbations
Although recurrent neural networks (RNNs) are state-of-the-art in numerous sequential decision-making tasks, there has been little research on explaining their predictions.
Control with adaptive Q-learning
The main difference between AQL and SPAQL is that the latter learns time-invariant policies, where the mapping from states to actions does not depend explicitly on the time step.
Variational Mixture of Normalizing Flows
The present work overcomes this by using normalizing flows as components in a mixture model and devising an end-to-end training procedure for such a model.
Equilibrium Propagation for Complete Directed Neural Networks
Artificial neural networks, one of the most successful approaches to supervised learning, were originally inspired by their biological counterparts.
Sparse and Continuous Attention Mechanisms
Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e. g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation).
Ranked #36 on
Visual Question Answering (VQA)
on VQA v2 test-std
Can auto-encoders help with filling missing data?
This paper introduces an approach to filling in missing data based on deep auto-encoder models, adequate to high-dimensional data exhibiting complex dependencies, such as images.
A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints
In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints.
End-to-End Learning of Video Compression Using Spatio-Temporal Autoencoders
Deep learning (DL) is having a revolutionary impact in image processing, with DL-based approaches now holding the state of the art in many tasks, including image compression.
Conditional Random Fields as Recurrent Neural Networks for 3D Medical Imaging Segmentation
In this paper, we test whether this algorithm, which was shown to improve semantic segmentation for 2D RGB images, is able to improve segmentation quality for 3D multi-modal medical images.
Scene-Adapted Plug-and-Play Algorithm with Guaranteed Convergence: Applications to Data Fusion in Imaging
The recently proposed plug-and-play (PnP) framework allows leveraging recent developments in image denoising to tackle other, more involved, imaging inverse problems.
Blind image deblurring using class-adapted image priors
Blind image deblurring (BID) is an ill-posed inverse problem, usually addressed by imposing prior knowledge on the (unknown) image and on the blurring filter.
Scene-adapted plug-and-play algorithm with convergence guarantees
Recent frameworks, such as the so-called plug-and-play, allow us to leverage the developments in image denoising to tackle other, and more involved, problems in image processing.
Image Restoration with Locally Selected Class-Adapted Models
State-of-the-art algorithms for imaging inverse problems (namely deblurring and reconstruction) are typically iterative, involving a denoising operation as one of its steps.
Image Restoration and Reconstruction using Variable Splitting and Class-adapted Image Priors
This paper proposes using a Gaussian mixture model as a prior, for solving two image inverse problems, namely image deblurring and compressive imaging.
The Ordered Weighted $\ell_1$ Norm: Atomic Formulation, Projections, and Algorithms
The ordered weighted $\ell_1$ norm (OWL) was recently proposed, with two different motivations: its good statistical properties as a sparsity promoting regularizer; the fact that it generalizes the so-called {\it octagonal shrinkage and clustering algorithm for regression} (OSCAR), which has the ability to cluster/group regression variables that are highly correlated.
Decreasing Weighted Sorted $\ell_1$ Regularization
We consider a new family of regularizers, termed {\it weighted sorted $\ell_1$ norms} (WSL1), which generalizes the recently introduced {\it octagonal shrinkage and clustering algorithm for regression} (OSCAR) and also contains the $\ell_1$ and $\ell_{\infty}$ norms as particular instances.
Spectrometric differentiation of yeast strains using minimum volume increase and minimum direction change clustering criteria
This paper proposes new clustering criteria for distinguishing Saccharomyces cerevisiae (yeast) strains using their spectrometric signature.
Exploiting Two-Dimensional Group Sparsity in 1-Bit Compressive Sensing
The subgradient of the 2D one-sided $\ell_1$ (or $\ell_2$) penalty and the projection onto the $K$-sparsity and TV or MTV constraint can be computed efficiently, allowing the appliaction of algorithms of the {\it forward-backward splitting} (a. k. a.
Binary Fused Compressive Sensing: 1-Bit Compressive Sensing meets Group Sparsity
We propose a new method, {\it binary fused compressive sensing} (BFCS), to recover sparse piece-wise smooth signals from 1-bit compressive measurements.
Group-sparse Matrix Recovery
We show that the proximity operator of 2OSCAR can be computed based on that of OSCAR.
Robust Binary Fused Compressive Sensing using Adaptive Outlier Pursuit
We propose a new method, {\it robust binary fused compressive sensing} (RoBFCS), to recover sparse piece-wise smooth signals from 1-bit compressive measurements.
A novel sparsity and clustering regularization
We propose a novel SPARsity and Clustering (SPARC) regularizer, which is a modified version of the previous octagonal shrinkage and clustering algorithm for regression (OSCAR), where, the proposed regularizer consists of a $K$-sparse constraint and a pair-wise $\ell_{\infty}$ norm restricted on the $K$ largest components in magnitude.
Solving OSCAR regularization problems by proximal splitting algorithms
The OSCAR regularizer has a non-trivial proximity operator, which limits its applicability.
